© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 75543
    Prev
    Next
    INDEX
    Explanations

    Poetic meter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     chirurg
    -0.07
     crédito
    -0.07
     automatique
    -0.07
     phosphate
    -0.07
    .cvt
    -0.07
    精
    -0.07
     faculty
    -0.07
     and
    -0.07
    ative
    -0.07
    ron
    -0.07
    POSITIVE LOGITS
     оказывает
    0.10
     debilit
    0.08
    gani
    0.08
     պահին
    0.08
     սկսել
    0.08
     verboten
    0.08
     נג
    0.08
     وکړئ
    0.08
     ك
    0.08
    indwa
    0.08
    Activations Density 0.003%

    No Known Activations